Wisp: small Llama-style base models trained from scratch on educational text and code.
DedeProGames PRO
DedeProGames
P(doom) <0.1%
AI & ML interests
Agentic & Coding finetune, Decoder-Onlys from Scratch, Image LoRAs, AI Researcher
Recent Activity
reacted to mithulaartigala's post with š¤ about 1 hour ago
I am LOVING HuggingFace Pro <3 reacted to theirpost with š about 2 hours ago
š Introducing OpenWork ā Deploy agents everywhere.
OpenWork is an open-source AI agent workspace built on top of OpenCode.
Deploy autonomous agents, schedule tasks, manage projects, and let AI work for you ā directly from your terminal.
Features:
- š¤ Deploy autonomous AI agents
- š
Schedule recurring tasks
- š§ Persistent memory and workspaces
- š MCP integrations and custom tools
- š„ Agent Inbox and task management
-ā” Support for local and cloud AI models
- š„ļø Interactive terminal interface (TUI)
Your agents. Your models. Your workflow.
Fully open-source. MIT licensed.
ā GitHub: https://github.com/dedeprogames-official/openwork
#OpenSource #AI #AIAgents #OpenWork #OpenCode
reacted to theirpost with š about 2 hours ago
š Introducing OpenWork ā Deploy agents everywhere.
OpenWork is an open-source AI agent workspace built on top of OpenCode.
Deploy autonomous agents, schedule tasks, manage projects, and let AI work for you ā directly from your terminal.
Features:
- š¤ Deploy autonomous AI agents
- š
Schedule recurring tasks
- š§ Persistent memory and workspaces
- š MCP integrations and custom tools
- š„ Agent Inbox and task management
-ā” Support for local and cloud AI models
- š„ļø Interactive terminal interface (TUI)
Your agents. Your models. Your workflow.
Fully open-source. MIT licensed.
ā GitHub: https://github.com/dedeprogames-official/openwork
#OpenSource #AI #AIAgents #OpenWork #OpenCode
Organizations
Kiyo: State-of-the-art models trained from scratch on vast amounts of web tokens, educational text, and code.
LowOnMind: Small decoder-only models trained in small amount of tokens
-
SLM-Archive/LowOnMind-8M
Text Generation ā¢ 8.06M ā¢ Updated ā¢ 823 ā¢ 2 -
SLM-Archive/LowOnMind-5M
Text Generation ā¢ 4.92M ā¢ Updated ā¢ 608 ā¢ 1 -
SLM-Archive/LowOnMind-1M
Text Generation ā¢ 985k ā¢ Updated ā¢ 384 ā¢ 3 -
SLM-Archive/LowOnMind-300k
Text Generation ā¢ 297k ā¢ Updated ā¢ 802 ā¢ 4
Small and Efficient Chess Models
GPT-U: small Llama-style base models trained from scratch on web, educational text and code, with fully open scripts, logs and evals.
DynamicMind: a family of lightweight models trained from scratch on diverse datasets.
Some experimental decoder-onlys made by me for research
-
SLM-Archive/NanoDex-Test-500K-200M
Text Generation ā¢ 492k ā¢ Updated ā¢ 1.01k ā¢ 1 -
SLM-Archive/NanoDex-1M
Text Generation ā¢ 1.06M ā¢ Updated ā¢ 1k ā¢ 1 -
SLM-Archive/Overaddicted-500K
Text Generation ā¢ 492k ā¢ Updated ā¢ 1.29k ā¢ 1 -
DedeProGames/Kiyo-Diffusion-135M
Text Generation ā¢ 0.1B ā¢ Updated ā¢ 102 ā¢ 2
Experimental medical model based on Qwen2.5 Family
Wisp: small Llama-style base models trained from scratch on educational text and code.
GPT-U: small Llama-style base models trained from scratch on web, educational text and code, with fully open scripts, logs and evals.
Kiyo: State-of-the-art models trained from scratch on vast amounts of web tokens, educational text, and code.
DynamicMind: a family of lightweight models trained from scratch on diverse datasets.
LowOnMind: Small decoder-only models trained in small amount of tokens
-
SLM-Archive/LowOnMind-8M
Text Generation ā¢ 8.06M ā¢ Updated ā¢ 823 ā¢ 2 -
SLM-Archive/LowOnMind-5M
Text Generation ā¢ 4.92M ā¢ Updated ā¢ 608 ā¢ 1 -
SLM-Archive/LowOnMind-1M
Text Generation ā¢ 985k ā¢ Updated ā¢ 384 ā¢ 3 -
SLM-Archive/LowOnMind-300k
Text Generation ā¢ 297k ā¢ Updated ā¢ 802 ā¢ 4
Some experimental decoder-onlys made by me for research
-
SLM-Archive/NanoDex-Test-500K-200M
Text Generation ā¢ 492k ā¢ Updated ā¢ 1.01k ā¢ 1 -
SLM-Archive/NanoDex-1M
Text Generation ā¢ 1.06M ā¢ Updated ā¢ 1k ā¢ 1 -
SLM-Archive/Overaddicted-500K
Text Generation ā¢ 492k ā¢ Updated ā¢ 1.29k ā¢ 1 -
DedeProGames/Kiyo-Diffusion-135M
Text Generation ā¢ 0.1B ā¢ Updated ā¢ 102 ā¢ 2
Experimental medical model based on Qwen2.5 Family
Small and Efficient Chess Models